Publish matched ReSeed release on main

README.md

@@ -0,0 +1,513 @@
+---
+license: other
+license_name: upstream-model-licenses-apply
+license_link: https://github.com/TWWinde/ReSeed/blob/main/NOTICE.md
+library_name: diffusers
+tags:
+- reseed
+- diffusion
+- distillation
+- text-to-image
+- text-to-video
+base_model:
+- stabilityai/stable-diffusion-3-medium-diffusers
+- stabilityai/stable-diffusion-3.5-medium
+- black-forest-labs/FLUX.1-dev
+- Wan-AI/Wan2.1-T2V-1.3B-Diffusers
+---
+
+# ReSeed — single-seed model weights
+
+**A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation**
+
+[Paper](https://arxiv.org/abs/2610.37110) · [Project page](https://twwinde.github.io/reseed-project-page/) · [Code](https://github.com/TWWinde/ReSeed)
+
+This branch contains four ReSeed bias adapters and the two self-trained DMD
+students needed to use the SD3 adapters. It is a **private, single-seed
+release**: every selected training run uses seed **42**. Use the
+**`main` revision** when downloading. The original `single-seed` branch is
+retained as a release snapshot.
+
+The SD3-Medium and SD3.5-Medium students were trained by the ReSeed authors.
+The FLUX and Wan students come from public releases by their respective
+authors. Public teacher models and shared components are referenced below,
+not copied into this repository.
+
+## Contents
+
+- [What ReSeed changes](#what-reseed-changes)
+- [Released checkpoints and model sources](#released-checkpoints-and-model-sources)
+- [Repository layout](#repository-layout)
+- [Environment and authentication](#environment-and-authentication)
+- [Download the release](#download-the-release)
+- [SD3-Medium and SD3.5-Medium inference](#sd3-medium-and-sd35-medium-inference)
+- [SenseFlow-FLUX inference](#senseflow-flux-inference)
+- [Wan2.1 text-to-video inference](#wan21-text-to-video-inference)
+- [Reproducibility and file verification](#reproducibility-and-file-verification)
+- [Troubleshooting](#troubleshooting)
+- [Limitations and licensing](#limitations-and-licensing)
+- [Citation](#citation)
+
+## What ReSeed changes
+
+ReSeed trains small, per-channel residual biases inside a frozen distilled
+student. At inference, the biases are active **only during the first of four
+denoising steps**. The original student weights remain unchanged, and the
+final three steps run without the biases. No teacher forward pass is needed
+when generating with the trained adapter.
+
+During adapter training, the student's first-step velocity is matched to
+the teacher's average velocity over the same time interval. This is a
+post-distillation correction; it does not repeat student distillation.
+
+The adapter is **not** a LoRA and is **not** a complete Diffusers pipeline.
+It must be loaded using the ReSeed adapter code and applied to the exact
+student it was fitted on. Do not load it with `load_lora_weights`, apply it
+to the teacher, or leave it active for all four steps.
+
+## Released checkpoints and model sources
+
+### Weights included in this branch
+
+| Model | Adapter training seed | Adapter update | Bias parameters | Matching student |
+| --- | ---: | ---: | ---: | --- |
+| SD3-Medium | 42 | **1900** | 72,192 | Our DMD, training seed 42, update 2000; included |
+| SD3.5-Medium | 42 | **2100** | 72,192 | Our DMD, training seed 42, update 2000; included |
+| SenseFlow-FLUX | 42 | **2000** | 233,472 | Public SenseFlow-FLUX; download separately |
+| Wan2.1-T2V-1.3B | 42 | **300** | 46,080 | Public Wan DMD2, iteration 1000; download separately |
+
+Adapter updates and student updates are different counters. For example,
+the SD3.5 adapter at update 2100 must be used with the included student at
+update 2000, not with an unrelated student checkpoint named `2100`.
+
+Three different seeds may appear in a workflow:
+
+1. **Student training seed:** selects our DMD student run; it is 42 here.
+2. **Adapter training seed:** selects the ReSeed fitting run; it is 42 here.
+3. **Generation seed:** selects the initial noise for an image or video.
+   This can be any supported seed, such as 0 or 1; it need not be 42.
+
+These are individual checkpoints, not averaged weights. One selected run
+does not by itself reproduce a three-training-seed aggregate in the paper.
+GAD and DP-DMD student weights are not included in this release.
+
+### Public teachers and external students
+
+| Component | Original source | Revision or checkpoint |
+| --- | --- | --- |
+| SD3-Medium teacher and shared components | [stabilityai/stable-diffusion-3-medium-diffusers](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers) | `ea42f8cef0f178587cf766dc8129abd379c90671` |
+| SD3.5-Medium teacher and shared components | [stabilityai/stable-diffusion-3.5-medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium) | `b940f670f0eda2d07fbb75229e779da1ad11eb80` |
+| FLUX teacher and shared components | [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) | `3de623fc3c33e44ffbe2bad470d0f45bccf2eb21` |
+| SenseFlow-FLUX student transformer | [domiso/SenseFlow](https://huggingface.co/domiso/SenseFlow) | Revision `1bbd81546d590acf24470b39ab28f9cd918c3927`, subfolder **`SenseFlow-FLUX`** |
+| Wan teacher and shared components | [Wan-AI/Wan2.1-T2V-1.3B-Diffusers](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers) | Original public teacher; see the video runtime setup |
+| Wan DMD2 student | [csusupergear/wan_t2v_checkpoints_release](https://huggingface.co/csusupergear/wan_t2v_checkpoints_release) | Prefix **`dmd2_t2v_vipe/0001000`**; retain its `.pth` and `.net_model.zip` files |
+
+The SenseFlow transformer is directly in `SenseFlow-FLUX`, not
+`SenseFlow-FLUX/transformer`. The Wan checkpoint uses the DFD/fastgen format;
+it is not a standalone Diffusers `transformer/` folder.
+
+The original SD3-M manifest retains the historical internal objective label
+`tdm`; its recorded implementation is `sd_distill_classic_v1`. Original
+manifests are preserved without silently changing their labels or paths.
+
+## Repository layout
+
+```text
+Wenwu2000/ReSeed (main)/
+├── README.md
+├── requirements.txt
+├── inference.py                  # Single-prompt SD3-M / SD3.5-M example
+├── release_manifest.json         # Pairings, sources, sizes and SHA-256 hashes
+├── adapters/
+│   ├── sd3m/seed_42/checkpoint-1900/
+│   ├── sd35m/seed_42/checkpoint-2100/
+│   ├── flux/seed_42/checkpoint-2000/
+│   └── wan21/seed_42/checkpoint-300/
+│       # Each adapter directory contains residual_biases.pt and manifest.json
+└── students/
+    ├── sd3m/seed_42/checkpoint-2000/
+    └── sd35m/seed_42/checkpoint-2000/
+        ├── manifest.json
+        └── student/
+            ├── config.json
+            ├── diffusion_pytorch_model-00001-of-00002.safetensors
+            ├── diffusion_pytorch_model-00002-of-00002.safetensors
+            └── diffusion_pytorch_model.safetensors.index.json
+```
+
+The complete release is approximately **18.22 GB** in decimal units. Most
+of that size is the two self-trained students. Their original inference
+files are retained without conversion or quantization. The adapters are small.
+
+This repository excludes optimizer state, fake-score models, teacher
+weights, text encoders, VAEs, datasets, prompt caches and generated media.
+It is an inference release, not a resumable training checkpoint archive.
+Absolute paths in original manifests are provenance records from our
+training system; users do not need to recreate those server paths.
+
+## Environment and authentication
+
+Use Python 3.10 or later and install PyTorch for your CUDA environment.
+The image inference examples target a CUDA GPU with BF16 support. FLUX
+also needs enough memory for its transformer, text encoders and VAE; the
+example generator does not automatically quantize or offload them.
+
+The image-side reference environment uses:
+
+| Package | Version |
+| --- | --- |
+| PyTorch | 2.6.0 in the original generation environment; install for your CUDA setup |
+| Diffusers | 0.34.0 |
+| Transformers | 4.45.2 |
+| Hugging Face Hub | 0.36.2 |
+
+Install the Hub CLI before downloading:
+
+```bash
+pip install huggingface_hub==0.36.2
+hf auth login
+hf auth whoami
+```
+
+Your account needs access to this private repository. Separately accept
+the terms of any gated upstream model before downloading its components.
+Access to ReSeed does not automatically grant access to Stability AI or
+FLUX checkpoints. Never write an access token into source code or a README.
+
+## Download the release
+
+Run the following from a working directory in which you want to keep the
+weights, upstream models and code:
+
+```bash
+hf download Wenwu2000/ReSeed --revision main --local-dir reseed-weights
+
+git clone https://github.com/TWWinde/ReSeed.git
+git -C ReSeed checkout eed9a03bd85a0af8a7dc36e8da5b48d2a31f58ca
+pip install -r reseed-weights/requirements.txt
+pip install -e ReSeed/image --no-deps
+```
+
+The code revision above is the public ReSeed version used by these examples.
+The weight repository itself does not install the `reseed` Python package.
+
+For SD3-Medium only, avoid downloading the other student:
+
+```bash
+hf download Wenwu2000/ReSeed --revision main --local-dir reseed-weights \
+  --include README.md requirements.txt inference.py release_manifest.json \
+  "adapters/sd3m/*" "students/sd3m/*"
+```
+
+Replace both `sd3m` patterns with `sd35m` for SD3.5-Medium. For FLUX or
+Wan, download `adapters/flux/*` or `adapters/wan21/*` and the documentation;
+their public students must still be obtained separately.
+
+Python can download the same branch without cloning a large Git repository:
+
+```python
+from huggingface_hub import snapshot_download
+
+weights = snapshot_download(
+    repo_id="Wenwu2000/ReSeed",
+    revision="main",
+    local_dir="reseed-weights",
+)
+print(weights)
+```
+
+## SD3-Medium and SD3.5-Medium inference
+
+### Download the matching public components
+
+```bash
+hf download stabilityai/stable-diffusion-3-medium-diffusers \
+  --revision ea42f8cef0f178587cf766dc8129abd379c90671 --local-dir models/sd3m
+
+hf download stabilityai/stable-diffusion-3.5-medium \
+  --revision b940f670f0eda2d07fbb75229e779da1ad11eb80 --local-dir models/sd35m
+```
+
+The example loads the included DMD transformer in place of the public
+teacher transformer. It reuses the public text encoders, tokenizers, VAE
+and scheduler. It does not run the teacher during student inference.
+
+### Generate with ReSeed
+
+```bash
+python reseed-weights/inference.py --weights reseed-weights --model sd3m \
+  --base models/sd3m --prompt "a photo of a cat" --seed 0 \
+  --output samples/sd3m_reseed_seed0.png
+
+python reseed-weights/inference.py --weights reseed-weights --model sd35m \
+  --base models/sd35m --prompt "a photo of a cat" --seed 0 \
+  --output samples/sd35m_reseed_seed0.png
+```
+
+`--base` is a **local upstream snapshot directory**. `--weights` is the
+downloaded ReSeed branch root. `--model sd3m` or `sd35m` selects the correct
+student and adapter from `release_manifest.json` automatically.
+
+### Generate the matched DMD baseline
+
+Use the same prompt and generation seed, and add `--without-reseed`:
+
+```bash
+python reseed-weights/inference.py --weights reseed-weights --model sd3m \
+  --base models/sd3m --prompt "a photo of a cat" --seed 0 \
+  --without-reseed --output samples/sd3m_dmd_seed0.png
+
+python reseed-weights/inference.py --weights reseed-weights --model sd35m \
+  --base models/sd35m --prompt "a photo of a cat" --seed 0 \
+  --without-reseed --output samples/sd35m_dmd_seed0.png
+```
+
+The baseline keeps the same DMD weights and initial noise; only the adapter
+is omitted. It is not a comparison against the public many-step teacher.
+The script refuses to overwrite an existing image, so use separate output names.
+
+### Fixed sampler and adapter behavior
+
+| Setting | Both SD3 student examples |
+| --- | --- |
+| Resolution | 1024×1024 |
+| Solver | Native FlowMatch Euler |
+| Number of steps | 4 |
+| Student CFG | **1** |
+| Scheduler | Static shift 3, dynamic shifting disabled |
+| Explicit unshifted sigmas | `[1.0, 0.75, 0.5, 0.25]` |
+| Text maximum sequence length | 256 |
+| Inference dtype | BF16 |
+| Initial noise | CPU FP32 Gaussian draw, then BF16 cast |
+| ReSeed gate | Active for step 1 only; disabled for steps 2–4 |
+
+The `sigmas` argument above is the **unshifted** schedule supplied to the
+pipeline; the scheduler applies its shift. Do not replace it with the
+already shifted values from an adapter manifest. Those manifests may also
+contain BF16-rounded training boundaries.
+
+The teacher references use **28 steps / CFG 7** for SD3-Medium and **40
+steps / CFG 4.5** for SD3.5-Medium. Those guidance settings must not replace
+the student's CFG 1. The adapter manifests record the exact first interval
+and teacher microstep settings used for fitting.
+
+For multiple samples, change `--seed` and the output filename. The example
+handles one prompt/sample per invocation and resets its gate for each run.
+The commands are process-level examples, not single-GPU Slurm submissions.
+Our MUSICA jobs request a whole four-H100 node and parallelize independent
+samples across its four GPUs.
+
+## SenseFlow-FLUX inference
+
+### Obtain FLUX components and the released student
+
+```bash
+hf download black-forest-labs/FLUX.1-dev \
+  --revision 3de623fc3c33e44ffbe2bad470d0f45bccf2eb21 --local-dir models/flux-dev
+
+hf download domiso/SenseFlow --revision 1bbd81546d590acf24470b39ab28f9cd918c3927 \
+  --include "SenseFlow-FLUX/*" --local-dir models/senseflow
+```
+
+Use the SenseFlow transformer, not the FLUX.1-dev transformer, with this
+adapter. The public FLUX snapshot provides shared components and the scheduler.
+
+### Prepare a prompt CSV
+
+Save the following as `prompts.csv` in the working directory:
+
+```csv
+case_number,evaluation_seed,prompt,prompt_id,sample_id
+0,0,a photo of a cat,0,0
+1,1,a photo of a cat,0,1
+```
+
+`case_number` must be unique. `evaluation_seed` is the generation noise
+seed. Rows for the same prompt share `prompt_id`; `sample_id` identifies
+the sample within that prompt. Quote the prompt field if it contains commas.
+
+### Generate SenseFlow + ReSeed
+
+```bash
+cd ReSeed/image
+python tools/flux_generate.py --model senseflow \
+  --dev-model ../../models/flux-dev \
+  --senseflow-transformer ../../models/senseflow/SenseFlow-FLUX \
+  --first-interval-residual-bias-checkpoint ../../reseed-weights/adapters/flux/seed_42/checkpoint-2000 \
+  --prompts ../../prompts.csv --expected-count 2 --samples-per-prompt 2 \
+  --evaluation-protocol reseed-single-seed-example \
+  --steps 4 --resolution 1024 --max-sequence-length 512 \
+  --output ../../samples/flux_reseed
+cd ../..
+```
+
+Omit `--first-interval-residual-bias-checkpoint` and use a different output
+directory for the plain SenseFlow baseline. Retain the same CSV and seeds.
+The generator writes images, a generation manifest and a protocol record.
+`reseed-single-seed-example` is an example run label, not a paper benchmark.
+
+The native student uses four dynamically shifted Euler steps, approximately
+`[1, .904531, .759511, .512844, 0]`, with BF16 inference and text length 512.
+Its guidance embedding is **disabled**: do not pass `--guidance 3.5` for
+SenseFlow. FLUX.1-dev guidance 3.5 belongs to the teacher target, not this
+student. The generator checks the schedule against Diffusers and activates
+the bias only during the first step.
+
+## Wan2.1 text-to-video inference
+
+### Set up DFD / fastgen
+
+The Wan adapter uses the DMD2 student in the
+[DFD checkpoint release](https://huggingface.co/csusupergear/wan_t2v_checkpoints_release)
+and runs through [DFD / fastgen](https://github.com/csy2077/data-forcing-distillation).
+Follow the [ReSeed video installation guide](https://github.com/TWWinde/ReSeed/blob/eed9a03bd85a0af8a7dc36e8da5b48d2a31f58ca/video/README.md)
+to install the ReSeed module and apply its inference patch to a configured
+DFD checkout. The image package alone is not sufficient for video generation.
+Use DFD's environment and public Wan component setup; do not assume that
+the image requirements file provides the complete video environment.
+
+### Download the public DMD2 checkpoint
+
+```bash
+hf download csusupergear/wan_t2v_checkpoints_release \
+  --include "dmd2_t2v_vipe/0001000*" --local-dir wan-checkpoints
+```
+
+Keep the original `.pth` and `.net_model.zip` filenames. DFD receives the
+checkpoint **prefix** `dmd2_t2v_vipe/0001000`, rather than a renamed weight
+file or a Diffusers pipeline directory.
+
+### Generate matched DMD2 and DMD2 + ReSeed videos
+
+Create a UTF-8 text file with one prompt per line, then run the following
+from the configured, patched DFD checkout:
+
+```bash
+export DFD_CKPT_ROOT=/absolute/path/to/wan-checkpoints
+export DFD_RESEED_ADAPTER=/absolute/path/to/reseed-weights/adapters/wan21/seed_42/checkpoint-300
+export DFD_PROMPT_FILE=/absolute/path/to/video-prompts.txt
+
+python evaluation/generate_multiseed.py --config evaluation/config.yaml \
+  --models dmd2 dmd2_reseed --seeds 0 1 \
+  --output-root evaluation/reseed-example
+```
+
+The driver passes `FASTGEN_RESEED_ADAPTER` to the patched inference process
+for the ReSeed arm. Setting `DFD_RESEED_ADAPTER` without installing that
+patch does not add ReSeed support to an unmodified inference script.
+
+| Setting | Wan DMD2 / DMD2 + ReSeed |
+| --- | --- |
+| Student solver | Native four-step ODE sampler |
+| Student time boundaries | `[.999, .937, .833, .624, 0]` |
+| Student CFG | None; no student CFG branch is evaluated |
+| Video size | 832×480 |
+| Frames / FPS | 81 / 16 |
+| Inference dtype | BF16 |
+| ReSeed gate | First step only |
+| Teacher reference | 50 steps, CFG 5, shift 5 |
+
+Do not substitute the public DFD post-trained checkpoint for DMD2: the
+included ReSeed adapter was fitted on **DMD2 iteration 1000**. The DFD
+post-trained model is a different comparison method, not this adapter's base.
+
+## Reproducibility and file verification
+
+`release_manifest.json` records each model's teacher source, student origin,
+selected adapter update, matching student path, training seed provenance,
+original checkpoint location and per-file SHA-256 hashes. Original
+checkpoint manifests remain beside their weights.
+The release manifest retains `revision: single-seed`, identifying the
+original release branch. The same checkpoint files are also available on
+`main`; their hashes and model pairings are unchanged.
+
+After a **full** download, verify all inference files listed in the manifest:
+
+```python
+import hashlib
+import json
+from pathlib import Path
+
+root = Path("reseed-weights")
+manifest = json.loads((root / "release_manifest.json").read_text())
+for entry in manifest["files"]:
+    path = root / entry["path"]
+    assert path.is_file(), f"Missing: {path}"
+    assert path.stat().st_size == entry["bytes"], f"Wrong size: {path}"
+    digest = hashlib.sha256()
+    with path.open("rb") as handle:
+        for block in iter(lambda: handle.read(8 * 1024 * 1024), b""):
+            digest.update(block)
+    assert digest.hexdigest() == entry["sha256"], f"Hash mismatch: {path}"
+print("All listed inference files verified.")
+```
+
+For a selective download, verify only the manifest entries you deliberately
+downloaded; the full check above will correctly report the omitted models
+as missing. Documentation can be updated independently of the weight
+manifest. Hashes identify the released files, not generated outputs.
+
+For comparisons, keep the prompt, initial noise, scheduler, number of steps,
+resolution, dtype and guidance unchanged, and toggle only ReSeed. A matching
+integer seed is not sufficient if different runtimes draw noise differently.
+The supplied image example explicitly draws FP32 noise on CPU before the
+model-dtype cast. Do not normalize or interpolate that noise unless this is
+an explicitly separate experiment.
+
+Exact pixel equality across hardware, attention kernels or library versions
+is not guaranteed. BF16/FP32 changes can also change generated samples.
+Use the reference environment and pinned public snapshots when checking a
+reported comparison. The example scripts are inference entry points; they
+do not by themselves run COCO quality scoring, diversity evaluation or VBench.
+
+## Troubleshooting
+
+| Symptom | Check |
+| --- | --- |
+| `401`, `403` or a private repository appears missing | Log in with an authorized account; check private-repo access and upstream gated-model approval separately. |
+| Missing weights in an old local download | Refresh the snapshot with `--revision main`; check any selective-download patterns. |
+| `No module named reseed` | Install `ReSeed/image` in the same Python environment used for inference. |
+| A LoRA loader rejects `residual_biases.pt` | Use the ReSeed residual-bias loader, not PEFT or `load_lora_weights`. |
+| Missing shard or incomplete student | Download both safetensor shards, their index and `config.json`; do not copy a single shard alone. |
+| SD3 sampler contract error | Use the matching pinned base, static shift 3, the supplied unshifted sigmas and student CFG 1. |
+| Unexpected FLUX guidance error | Use `--model senseflow`, the `SenseFlow-FLUX` folder, and no guidance embedding. |
+| Wan adapter is ignored | Install the ReSeed inference patch and use the `dmd2_reseed` arm. |
+| Wan checkpoint loader fails | Preserve the public `.pth` / `.net_model.zip` pair and pass the correct checkpoint prefix. |
+| CUDA out of memory | Check which model is loaded and available GPU memory. The example does not silently change resolution, precision, quantization or offload settings. |
+| Output image already exists | Select a new output filename; the SD3 example intentionally refuses overwrites. |
+
+## Limitations and licensing
+
+These adapters are tied to their listed students and native sampling
+settings. Applying one to another backbone, another distillation run, a
+different step count or a different resolution is outside this release's
+documented setup. A diversity gain on an evaluation bank does not guarantee
+that every prompt, quality metric or generated sample improves.
+
+This branch provides one selected run per model, not training data, complete
+training state or all experimental variants. It does not include weights
+for GAD, DP-DMD, SDXL or MiniMax experiments.
+
+The ReSeed implementation is MIT-licensed in the code repository. That does
+**not** replace the licenses of model weights or dependencies. Consult each
+linked upstream model's terms and the code repository's
+[NOTICE](https://github.com/TWWinde/ReSeed/blob/eed9a03bd85a0af8a7dc36e8da5b48d2a31f58ca/NOTICE.md).
+Keeping this repository private does not grant additional redistribution or
+commercial-use rights. This documentation update does not make the repository public.
+
+## Citation
+
+```bibtex
+@misc{tang2026reseed,
+  title={A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation},
+  author={Wenwu Tang and Dong Wang and Yun Cheng and Olga Saukh},
+  year={2026},
+  eprint={2610.37110},
+  archivePrefix={arXiv},
+  primaryClass={cs.CV},
+  url={https://arxiv.org/abs/2610.37110}
+}
+```
+
+Please also acknowledge the teacher models, external distilled students
+and DFD / fastgen software when using them in a new study.

adapters/flux/seed_42/checkpoint-2000/manifest.json

@@ -0,0 +1,145 @@
+{
+  "method": "flux-first-interval-block-residual-bias",
+  "student": "/data/fs201205/wt93384/models/SenseFlow/SenseFlow-FLUX",
+  "student_components_and_schedule": "/data/fs201205/wt93384/huggingface/hub/models--black-forest-labs--FLUX.1-dev/snapshots/3de623fc3c33e44ffbe2bad470d0f45bccf2eb21",
+  "student_transformer": "/data/fs201205/wt93384/models/SenseFlow/SenseFlow-FLUX",
+  "teacher": "/data/fs201205/wt93384/huggingface/hub/models--black-forest-labs--FLUX.1-dev/snapshots/3de623fc3c33e44ffbe2bad470d0f45bccf2eb21",
+  "teacher_target_cache": "/data/fs201205/wt93384/project/CRRA/outputs/first_interval_residual_bias_training_length_multiseed_coco5k_v1/seed_42/senseflow_teacher_cache",
+  "teacher_loaded": false,
+  "residual_definition": "double-block (text, image) outputs and single-block output plus learned per-channel biases",
+  "zero_initialized": true,
+  "double_blocks": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18
+  ],
+  "single_blocks": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37
+  ],
+  "bias_width": 3072,
+  "trainable_parameters": 233472,
+  "total_student_parameters": 11891178560,
+  "student_boundaries": [
+    1.0,
+    0.9045307636260986,
+    0.7595109343528748,
+    0.5128441452980042,
+    0.0
+  ],
+  "student_sigma0": 1.0,
+  "student_sigma1": 0.9045307636260986,
+  "teacher_micro_steps": 7,
+  "teacher_micro_sigmas": [
+    1.0,
+    0.988408625125885,
+    0.9762224555015564,
+    0.9633944630622864,
+    0.9498725533485413,
+    0.9355989098548889,
+    0.9205089807510376,
+    0.9045307636260986
+  ],
+  "teacher_guidance_scale": 3.5,
+  "teacher_max_sequence_length": 512,
+  "student_max_sequence_length": 512,
+  "student_guidance": null,
+  "adapter_scope": "first student interval only; disable for suffix intervals",
+  "world_size": 4,
+  "batch_size_per_rank": 1,
+  "global_batch_size": 4,
+  "gradient_checkpointing": true,
+  "loss": "MSE(student velocity at sigma0 with bias, teacher interval secant velocity)",
+  "resume_from_checkpoint": null,
+  "start_step": 0,
+  "schedule": {
+    "num_inference_steps": 4,
+    "image_seq_len": 4096,
+    "unshifted_sigmas": [
+      1.0,
+      0.75,
+      0.5,
+      0.25
+    ],
+    "sigmas": [
+      1.0,
+      0.9045307636260986,
+      0.7595109343528748,
+      0.5128441452980042,
+      0.0
+    ],
+    "timesteps": [
+      1000.0,
+      904.5307636260986,
+      759.5109343528748,
+      512.8441452980042
+    ],
+    "use_dynamic_shifting": true,
+    "time_shift_type": "exponential",
+    "mu": 1.15,
+    "static_shift": 3.0,
+    "base_shift": 0.5,
+    "max_shift": 1.15,
+    "base_image_seq_len": 256,
+    "max_image_seq_len": 4096,
+    "num_train_timesteps": 1000,
+    "sigma_convention": "x_sigma = (1 - sigma) * x0 + sigma * epsilon; v = epsilon - x0"
+  },
+  "step": 2000,
+  "bias_rms": 0.17543458938598633,
+  "bias_abs_mean": 0.1268637627363205,
+  "bias_abs_max": 1.10356605052948,
+  "bias_parameter_count": 233472
+}

adapters/flux/seed_42/checkpoint-2000/residual_biases.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d4900cc8fe3af15229f50e8777057d05c1eea1586e2f684594ca944be8a57b
+size 958322

adapters/sd35m/seed_42/checkpoint-2100/manifest.json

@@ -0,0 +1,113 @@
+{
+  "method": "sd3m-first-interval-block-residual-bias",
+  "base_student": "/data/fs201205/wt93384/project/CRRA/outputs/musica_sd35m1024_dmd_only_unified_3seed_v1/sd35m_dmd_teacher_cfg_w4p5/seed_42/checkpoint-2000",
+  "teacher": "/data/fs201205/wt93384/huggingface/hub/models--stabilityai--stable-diffusion-3.5-medium/snapshots/b940f670f0eda2d07fbb75229e779da1ad11eb80",
+  "residual_definition": "image/context block output plus learned channel bias",
+  "zero_initialized": true,
+  "blocks": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23
+  ],
+  "image_widths": {
+    "0": 1536,
+    "1": 1536,
+    "2": 1536,
+    "3": 1536,
+    "4": 1536,
+    "5": 1536,
+    "6": 1536,
+    "7": 1536,
+    "8": 1536,
+    "9": 1536,
+    "10": 1536,
+    "11": 1536,
+    "12": 1536,
+    "13": 1536,
+    "14": 1536,
+    "15": 1536,
+    "16": 1536,
+    "17": 1536,
+    "18": 1536,
+    "19": 1536,
+    "20": 1536,
+    "21": 1536,
+    "22": 1536,
+    "23": 1536
+  },
+  "context_widths": {
+    "0": 1536,
+    "1": 1536,
+    "2": 1536,
+    "3": 1536,
+    "4": 1536,
+    "5": 1536,
+    "6": 1536,
+    "7": 1536,
+    "8": 1536,
+    "9": 1536,
+    "10": 1536,
+    "11": 1536,
+    "12": 1536,
+    "13": 1536,
+    "14": 1536,
+    "15": 1536,
+    "16": 1536,
+    "17": 1536,
+    "18": 1536,
+    "19": 1536,
+    "20": 1536,
+    "21": 1536,
+    "22": 1536,
+    "23": null
+  },
+  "trainable_parameters": 72192,
+  "total_student_parameters": 2243171520,
+  "teacher_micro_steps": 10,
+  "teacher_guidance_scale": 4.5,
+  "teacher_cfg_threshold": 0.96,
+  "student_guidance_scale": 1.0,
+  "student_steps": 4,
+  "student_boundaries": [
+    1.0,
+    0.8984375,
+    0.75,
+    0.5,
+    0.0
+  ],
+  "interval_index": 0,
+  "trained_intervals": [
+    0
+  ],
+  "adapter_scope": "first student interval only; disable for suffix intervals",
+  "training_input_state": "initial noise",
+  "world_size": 4,
+  "batch_size_per_rank": 1,
+  "global_batch_size": 4,
+  "loss": "MSE(student velocity at sigma_k, teacher interval-k secant velocity)",
+  "step": 2100,
+  "bias_rms": 0.0999305248260498,
+  "bias_abs_mean": 0.07063129544258118,
+  "bias_abs_max": 0.6684044003486633
+}

adapters/sd35m/seed_42/checkpoint-2100/residual_biases.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73be99c79cb7f7b3a4cec9af059177179efeccb1c7ea8d47211c517be1ed6be
+size 304289

adapters/sd3m/seed_42/checkpoint-1900/manifest.json

@@ -0,0 +1,113 @@
+{
+  "method": "sd3m-first-interval-block-residual-bias",
+  "base_student": "/data/fs201205/wt93384/project/CRRA/outputs/musica_sd3m1024_tdm_teacher_cfg_scale_v1/sd3m_tdm_teacher_cfg_w7_1024/seed_42/checkpoint-2000",
+  "teacher": "/data/fs201205/wt93384/huggingface/hub/models--stabilityai--stable-diffusion-3-medium-diffusers/snapshots/ea42f8cef0f178587cf766dc8129abd379c90671",
+  "residual_definition": "image/context block output plus learned channel bias",
+  "zero_initialized": true,
+  "blocks": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23
+  ],
+  "image_widths": {
+    "0": 1536,
+    "1": 1536,
+    "2": 1536,
+    "3": 1536,
+    "4": 1536,
+    "5": 1536,
+    "6": 1536,
+    "7": 1536,
+    "8": 1536,
+    "9": 1536,
+    "10": 1536,
+    "11": 1536,
+    "12": 1536,
+    "13": 1536,
+    "14": 1536,
+    "15": 1536,
+    "16": 1536,
+    "17": 1536,
+    "18": 1536,
+    "19": 1536,
+    "20": 1536,
+    "21": 1536,
+    "22": 1536,
+    "23": 1536
+  },
+  "context_widths": {
+    "0": 1536,
+    "1": 1536,
+    "2": 1536,
+    "3": 1536,
+    "4": 1536,
+    "5": 1536,
+    "6": 1536,
+    "7": 1536,
+    "8": 1536,
+    "9": 1536,
+    "10": 1536,
+    "11": 1536,
+    "12": 1536,
+    "13": 1536,
+    "14": 1536,
+    "15": 1536,
+    "16": 1536,
+    "17": 1536,
+    "18": 1536,
+    "19": 1536,
+    "20": 1536,
+    "21": 1536,
+    "22": 1536,
+    "23": null
+  },
+  "trainable_parameters": 72192,
+  "total_student_parameters": 2028328000,
+  "teacher_micro_steps": 7,
+  "teacher_guidance_scale": 7.0,
+  "teacher_cfg_threshold": 0.96,
+  "student_guidance_scale": 1.0,
+  "student_steps": 4,
+  "student_boundaries": [
+    1.0,
+    0.8984375,
+    0.75,
+    0.5,
+    0.0
+  ],
+  "interval_index": 0,
+  "trained_intervals": [
+    0
+  ],
+  "adapter_scope": "first student interval only; disable for suffix intervals",
+  "training_input_state": "initial noise",
+  "world_size": 4,
+  "batch_size_per_rank": 1,
+  "global_batch_size": 4,
+  "loss": "MSE(student velocity at sigma_k, teacher interval-k secant velocity)",
+  "step": 1900,
+  "bias_rms": 0.08465656638145447,
+  "bias_abs_mean": 0.062301263213157654,
+  "bias_abs_max": 0.6448525786399841
+}

adapters/sd3m/seed_42/checkpoint-1900/residual_biases.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bebc02a72af7855e3f5c06548e570c96dcf3bd126820a4888757d633f9b6911
+size 304289

adapters/wan21/seed_42/checkpoint-300/manifest.json

@@ -0,0 +1,84 @@
+{
+  "method": "reseed-wan-first-interval-block-residual-bias",
+  "student_checkpoint": "/data/fs201205/wt93384/project/DFD/checkpoints/dmd2_t2v_vipe/0001000",
+  "student_ckpt_iter": 1000,
+  "teacher": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
+  "t_list": [
+    0.999,
+    0.937,
+    0.833,
+    0.624,
+    0.0
+  ],
+  "shift": 5.0,
+  "active_interval": 0,
+  "micro_steps": 13,
+  "teacher_grid": [
+    0.999,
+    0.9951162964811582,
+    0.9911105196451203,
+    0.9869768220448105,
+    0.9827089767076683,
+    0.9783003458366588,
+    0.9737438463619149,
+    0.9690319119669876,
+    0.9641564511614891,
+    0.9591088009114213,
+    0.9538796752681936,
+    0.948459108355477,
+    0.9428363909774437,
+    0.937
+  ],
+  "teacher_guidance_scale": 5.0,
+  "student_guidance_scale": null,
+  "blocks": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29
+  ],
+  "trainable_parameters": 46080,
+  "student_parameters": 1418996800,
+  "embeddings": "/data/fs201205/wt93384/project/DFD/reseed_data/vipe_long/umt5_embeddings.pt",
+  "captions_sha256": "9058c6ecbbd634d60bcc13d2487fccb4d2cb98316cfd5fe6f89d16d54399f51c",
+  "n_prompts": 4000,
+  "world_size": 4,
+  "batch_per_rank": 1,
+  "global_batch": 4,
+  "gradient_checkpointing": true,
+  "loss": "MSE(student first-step velocity, teacher boundary-aligned secant velocity)",
+  "lr": 0.001,
+  "max_steps": 2000,
+  "seed": 42,
+  "step": 300,
+  "bias_rms": 0.014174574054777622,
+  "bias_abs_mean": 0.010956005193293095,
+  "bias_abs_max": 0.07245294004678726,
+  "num_parameters": 46080
+}

adapters/wan21/seed_42/checkpoint-300/residual_biases.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3ba005c6a473d567a7bd7235a2f11b441e9e7d82451c359b1e36072d52a1a7
+size 193868

inference.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+"""Single-prompt SD3-M / SD3.5-M generation with the matched released adapter.
+
+Install the image package from https://github.com/TWWinde/ReSeed first.
+No remote Python model code is loaded by this script.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--weights", type=Path, required=True, help="downloaded single-seed snapshot")
+    parser.add_argument("--model", choices=["sd3m", "sd35m"], required=True)
+    parser.add_argument("--base", type=Path, required=True, help="downloaded upstream teacher snapshot")
+    parser.add_argument("--prompt", required=True)
+    parser.add_argument("--seed", type=int, default=0, help="generation noise seed, not training seed")
+    parser.add_argument("--output", type=Path, required=True)
+    parser.add_argument("--without-reseed", action="store_true")
+    args = parser.parse_args()
+    if args.output.exists():
+        raise FileExistsError("refusing to overwrite an existing image")
+    import torch
+    from diffusers import StableDiffusion3Pipeline, SD3Transformer2DModel
+    from reseed.models.sd3_residual_bias import load_sd3_residual_bias_adapter
+
+    entry = json.loads((args.weights/"release_manifest.json").read_text())["models"][args.model]
+    transformer = SD3Transformer2DModel.from_pretrained(
+        str(args.weights/entry["student_path"]/"student"), torch_dtype=torch.bfloat16)
+    pipe = StableDiffusion3Pipeline.from_pretrained(str(args.base), transformer=transformer,
+                                                   torch_dtype=torch.bfloat16).to("cuda")
+    if abs(float(pipe.scheduler.config.shift)-3.) > 1e-7 or pipe.scheduler.config.get("use_dynamic_shifting", False):
+        raise ValueError("this release uses static FlowMatch shift=3, not dynamic shifting")
+    for component in pipe.components.values():
+        if isinstance(component, torch.nn.Module):
+            component.eval().requires_grad_(False)
+    adapter = None
+    if not args.without_reseed:
+        adapter, _ = load_sd3_residual_bias_adapter(pipe.transformer, args.weights/entry["adapter_path"])
+        adapter.to("cuda").eval().requires_grad_(False)
+        adapter.enable()
+    def callback(_pipe, index, _timestep, kwargs):
+        if adapter is not None:
+            adapter.disable()  # Step zero just finished; never activate on steps 1–3.
+        return kwargs
+    shape = (1, int(transformer.config.in_channels), 1024//pipe.vae_scale_factor, 1024//pipe.vae_scale_factor)
+    noise = torch.randn(shape, generator=torch.Generator(device="cpu").manual_seed(args.seed), dtype=torch.float32)
+    try:
+        with torch.inference_mode():
+            image = pipe(prompt=[args.prompt], negative_prompt=[""], height=1024, width=1024,
+                         sigmas=[1., .75, .5, .25], guidance_scale=1., max_sequence_length=256,
+                         latents=noise.to(device="cuda", dtype=torch.bfloat16),
+                         callback_on_step_end=callback if adapter is not None else None,
+                         callback_on_step_end_tensor_inputs=["latents"]).images[0]
+        args.output.parent.mkdir(parents=True, exist_ok=True)
+        image.save(args.output)
+    finally:
+        if adapter is not None:
+            adapter.disable(); adapter.close()
+
+
+if __name__ == "__main__":
+    main()

release_manifest.json

@@ -0,0 +1,210 @@
+{
+  "repository": "Wenwu2000/ReSeed",
+  "revision": "single-seed",
+  "private": true,
+  "seed": 42,
+  "source_commit": "83c7c7acd5b791df40bfc3c6cac9ca9271602a1f",
+  "models": {
+    "sd3m": {
+      "teacher": "stabilityai/stable-diffusion-3-medium-diffusers",
+      "teacher_revision": "ea42f8cef0f178587cf766dc8129abd379c90671",
+      "adapter_step": 1900,
+      "adapter_type": "sd3-block-residual-bias-v1",
+      "parameters": 72192,
+      "teacher_steps": 28,
+      "teacher_guidance": 7.0,
+      "student_guidance": 1.0,
+      "adapter_training_seed": 42,
+      "adapter_path": "adapters/sd3m/seed_42/checkpoint-1900",
+      "source_adapter": "/data/fs201205/wt93384/project/CRRA/outputs/first_interval_residual_bias_training_length_100step_v1/sd3m/checkpoint-1900",
+      "inference_steps": 4,
+      "active_bias_steps": [
+        0
+      ],
+      "adapter_seed_provenance": "original experiment run selection; checkpoint manifest omits seed",
+      "student_origin": "trained by the ReSeed authors",
+      "student_training_seed": 42,
+      "student_path": "students/sd3m/seed_42/checkpoint-2000",
+      "student_step": 2000,
+      "source_student": "/data/fs201205/wt93384/project/CRRA/outputs/musica_sd3m1024_tdm_teacher_cfg_scale_v1/sd3m_tdm_teacher_cfg_w7_1024/seed_42/checkpoint-2000",
+      "original_student_manifest_objective": "tdm"
+    },
+    "sd35m": {
+      "teacher": "stabilityai/stable-diffusion-3.5-medium",
+      "teacher_revision": "b940f670f0eda2d07fbb75229e779da1ad11eb80",
+      "adapter_step": 2100,
+      "adapter_type": "sd3-block-residual-bias-v1",
+      "parameters": 72192,
+      "teacher_steps": 40,
+      "teacher_guidance": 4.5,
+      "student_guidance": 1.0,
+      "adapter_training_seed": 42,
+      "adapter_path": "adapters/sd35m/seed_42/checkpoint-2100",
+      "source_adapter": "/data/fs201205/wt93384/project/CRRA/outputs/musica_sd35m1024_dmd_reseed_3seed_v1/seed_42/checkpoint-2100",
+      "inference_steps": 4,
+      "active_bias_steps": [
+        0
+      ],
+      "adapter_seed_provenance": "original experiment run selection; checkpoint manifest omits seed",
+      "student_origin": "trained by the ReSeed authors",
+      "student_training_seed": 42,
+      "student_path": "students/sd35m/seed_42/checkpoint-2000",
+      "student_step": 2000,
+      "source_student": "/data/fs201205/wt93384/project/CRRA/outputs/musica_sd35m1024_dmd_only_unified_3seed_v1/sd35m_dmd_teacher_cfg_w4p5/seed_42/checkpoint-2000",
+      "original_student_manifest_objective": "dmd"
+    },
+    "flux": {
+      "teacher": "black-forest-labs/FLUX.1-dev",
+      "teacher_revision": "3de623fc3c33e44ffbe2bad470d0f45bccf2eb21",
+      "public_student": "domiso/SenseFlow",
+      "public_student_subfolder": "SenseFlow-FLUX",
+      "public_student_revision": "1bbd81546d590acf24470b39ab28f9cd918c3927",
+      "adapter_step": 2000,
+      "adapter_type": "flux-block-residual-bias-v1",
+      "parameters": 233472,
+      "teacher_steps": 28,
+      "teacher_guidance": 3.5,
+      "student_guidance": null,
+      "adapter_training_seed": 42,
+      "adapter_path": "adapters/flux/seed_42/checkpoint-2000",
+      "source_adapter": "/data/fs201205/wt93384/project/CRRA/outputs/first_interval_residual_bias_training_length_multiseed_coco5k_v1/seed_42/senseflow/checkpoint-2000",
+      "inference_steps": 4,
+      "active_bias_steps": [
+        0
+      ],
+      "adapter_seed_provenance": "original experiment run selection; checkpoint manifest omits seed",
+      "student_origin": "public release; not trained by the ReSeed authors"
+    },
+    "wan21": {
+      "teacher": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
+      "public_student": "csusupergear/wan_t2v_checkpoints_release",
+      "public_student_prefix": "dmd2_t2v_vipe/0001000",
+      "adapter_step": 300,
+      "adapter_type": "wan-block-residual-bias-v1",
+      "parameters": 46080,
+      "teacher_steps": 50,
+      "teacher_guidance": 5.0,
+      "student_guidance": null,
+      "adapter_training_seed": 42,
+      "adapter_path": "adapters/wan21/seed_42/checkpoint-300",
+      "source_adapter": "/data/fs201205/wt93384/project/DFD/reseed_runs/dmd2_m13/checkpoint-300",
+      "inference_steps": 4,
+      "active_bias_steps": [
+        0
+      ],
+      "adapter_seed_provenance": "original checkpoint manifest",
+      "student_origin": "public release; not trained by the ReSeed authors"
+    }
+  },
+  "files": [
+    {
+      "path": "adapters/sd3m/seed_42/checkpoint-1900/manifest.json",
+      "bytes": 2260,
+      "sha256": "de158b7ea349b011035b99c7144e91d9aee17eedb91cb2ae58eb98f410e67891",
+      "git_blob_oid": "0d43708c574ef62b28694e89a56b90fd8587dcd1"
+    },
+    {
+      "path": "adapters/sd3m/seed_42/checkpoint-1900/residual_biases.pt",
+      "bytes": 304289,
+      "sha256": "9bebc02a72af7855e3f5c06548e570c96dcf3bd126820a4888757d633f9b6911",
+      "git_blob_oid": "5a554c456004c465ad0a4b334f932bf421b4e8d5"
+    },
+    {
+      "path": "students/sd3m/seed_42/checkpoint-2000/manifest.json",
+      "bytes": 1915,
+      "sha256": "fcbc2852a599e9ad393f944d1f59da524c2561e16f543c50628d8cc6e55f869a",
+      "git_blob_oid": "8515600f4b4aa6e5044e63bdfc0396463854542d"
+    },
+    {
+      "path": "students/sd3m/seed_42/checkpoint-2000/student/config.json",
+      "bytes": 598,
+      "sha256": "996e2e1fa2461bace40ec1ee6dd1d3a97e7cbb2fc8ce1ff16beba50bc60adb1b",
+      "git_blob_oid": "2391e4dba5fe495c1248efa662eccec6984ca3d6"
+    },
+    {
+      "path": "students/sd3m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00001-of-00002.safetensors",
+      "bytes": 4968557944,
+      "sha256": "ec1671c638ae2dca1f48e421e1d1493a9e7357d156b7b8c5536d042133ecd22f",
+      "git_blob_oid": "a8d029a21bfb02e8864841a280fe4d466e7a0e4f"
+    },
+    {
+      "path": "students/sd3m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00002-of-00002.safetensors",
+      "bytes": 3371325672,
+      "sha256": "f6c7195a4537e8cd3e104d2f8ac71006b57efe4b975a0b7af1c052b393783760",
+      "git_blob_oid": "3955675977258951b8c31512bc2ea24e33df6df4"
+    },
+    {
+      "path": "students/sd3m/seed_42/checkpoint-2000/student/diffusion_pytorch_model.safetensors.index.json",
+      "bytes": 70346,
+      "sha256": "49fe76c47ede8a13cb69a1d9225db3838581ed560c61be8f9730de6a2b1a25e0",
+      "git_blob_oid": "1acb02c4a494549e61dada64589c02dd06629998"
+    },
+    {
+      "path": "adapters/sd35m/seed_42/checkpoint-2100/manifest.json",
+      "bytes": 2251,
+      "sha256": "6d3b7cdde26f0d6b916d21c5f2e9a54097215a76810bfb4df32f2d1610217f84",
+      "git_blob_oid": "fba9c31599b968633ce9d810b1f9ca6807a5621c"
+    },
+    {
+      "path": "adapters/sd35m/seed_42/checkpoint-2100/residual_biases.pt",
+      "bytes": 304289,
+      "sha256": "f73be99c79cb7f7b3a4cec9af059177179efeccb1c7ea8d47211c517be1ed6be",
+      "git_blob_oid": "b5270c1e42aa2659bcd98f05f42977c6ed50a0b0"
+    },
+    {
+      "path": "students/sd35m/seed_42/checkpoint-2000/manifest.json",
+      "bytes": 2667,
+      "sha256": "f6de42ab0ecc9a1f85e50ea97932d2a7b5951c90a32c07e8ccfb00dc397bc749",
+      "git_blob_oid": "517bbc90e21f50b8f40ed6f636d113044e4c84ea"
+    },
+    {
+      "path": "students/sd35m/seed_42/checkpoint-2000/student/config.json",
+      "bytes": 692,
+      "sha256": "d06c28fa90d244dcf9369f7e0d800af28a4a6e7e01b9d6c628ab4224cad7b53e",
+      "git_blob_oid": "1b7e6fd009d65df9cd17556b111d55bca70d813f"
+    },
+    {
+      "path": "students/sd35m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00001-of-00002.safetensors",
+      "bytes": 4987168128,
+      "sha256": "b2bcda7066ac23650cd4f2a51b9b5a7526c1174c6eba2a44e2f1424465b1e1f0",
+      "git_blob_oid": "ad41008edd538ec59bd412cc7d172f1c344d3a23"
+    },
+    {
+      "path": "students/sd35m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00002-of-00002.safetensors",
+      "bytes": 4891592464,
+      "sha256": "80dc4e268bc80e51b60d7e327a133cea43240266841cecf6fe9eb777fc54ea02",
+      "git_blob_oid": "40b1a37c4c6d26de4ab43c31035ec11614cdf321"
+    },
+    {
+      "path": "students/sd35m/seed_42/checkpoint-2000/student/diffusion_pytorch_model.safetensors.index.json",
+      "bytes": 93468,
+      "sha256": "8de30e9468237e2789792637596a36f34e4eca15907162a601658e14dd610b6d",
+      "git_blob_oid": "ccb504a212f6deb16caa8a4aa42930987e524924"
+    },
+    {
+      "path": "adapters/flux/seed_42/checkpoint-2000/manifest.json",
+      "bytes": 3235,
+      "sha256": "588f0bdbb38f93bad34129724ade32cccdcd6eb4b0753b7d72d5142dc1242086",
+      "git_blob_oid": "d633a547bc47c053d74c3deff28c69b91669be53"
+    },
+    {
+      "path": "adapters/flux/seed_42/checkpoint-2000/residual_biases.pt",
+      "bytes": 958322,
+      "sha256": "d4d4900cc8fe3af15229f50e8777057d05c1eea1586e2f684594ca944be8a57b",
+      "git_blob_oid": "0f4d310821417eb21b6393f21b764a70db6fa02c"
+    },
+    {
+      "path": "adapters/wan21/seed_42/checkpoint-300/manifest.json",
+      "bytes": 1685,
+      "sha256": "e6075a110c5c12d21eb7cad200df6aa12cde76242996ea9990760c4d9c0284bc",
+      "git_blob_oid": "0e644bd621bdfb6a2a3d241dcc80ab806b5ac625"
+    },
+    {
+      "path": "adapters/wan21/seed_42/checkpoint-300/residual_biases.pt",
+      "bytes": 193868,
+      "sha256": "1f3ba005c6a473d567a7bd7235a2f11b441e9e7d82451c359b1e36072d52a1a7",
+      "git_blob_oid": "00e707a4c4769b94d3a57d944ddbeb13cd402daf"
+    }
+  ],
+  "scope": "Two self-trained DMD students; four matching ReSeed adapters; no public base weights or training state."
+}

requirements.txt

@@ -0,0 +1,10 @@
+# Install PyTorch for your CUDA environment before these packages.
+diffusers==0.34.0
+transformers==4.45.2
+accelerate>=1.2
+huggingface_hub==0.36.2
+safetensors>=0.4
+sentencepiece
+protobuf
+numpy
+Pillow

students/sd35m/seed_42/checkpoint-2000/manifest.json

@@ -0,0 +1,68 @@
+{
+  "backend": "sd35m-native",
+  "config_sha256": "e764fa04eec4da4e98c55b9e75e018109971328a0ce6946cf0ca9baa959d748d",
+  "cross_engine_resume_supported": false,
+  "distributed_world_size": 4,
+  "fake_score_layout": "fake_score",
+  "flow_contract": {
+    "antipodal_teacher_reg": {},
+    "crra_lpips_net": null,
+    "crra_lpips_version": null,
+    "crra_state_distance": "mse",
+    "data_forcing": {
+      "enabled": false
+    },
+    "dmd_cfg_control": 0.96,
+    "dmd_implementation": "sd_distill_classic_v1",
+    "dmd_loss_weighting": "channel_height_mean_keep_width",
+    "dmd_method": "classic",
+    "dmd_sigma_sampling": "points_mode_c",
+    "dmd_student_fake_sample_coupling": "reuse_last_fake_rollout",
+    "dmd_student_gradient_scope": "local_interval",
+    "fake_score_guidance_scale": 1.0,
+    "fake_teacher_anchor_enabled": false,
+    "fake_updates_per_student": 5,
+    "gad_nsp": {
+      "lambda_nsp": 0.0
+    },
+    "global_unique_prompts_per_student_update": 4,
+    "guidance_mode": "classic_cfg_no_slg",
+    "initial_rollout_noise": "gaussian",
+    "initial_rollout_noise_lowpass_cutoff": null,
+    "initial_rollout_noise_lowpass_fraction": null,
+    "initial_rollout_noise_normalization": null,
+    "initial_rollout_noise_pairing": null,
+    "initial_rollout_noise_support": "full Gaussian",
+    "lambda_fake_teacher_reg": 0.0,
+    "nsp_perturbation": "x_plus_epsilon_v; v~N(0,I) in FP32; fixed detached flow state",
+    "reference_inference_steps": 40,
+    "repulsive_expected_pairwise_correlation": null,
+    "repulsive_group_size": null,
+    "shift": 3.0,
+    "student_forwards_per_step": 1,
+    "student_guidance_scale": 1.0,
+    "student_sigma_grid": "uniform_unshifted",
+    "student_steps": 4,
+    "teacher_cfg_symmetric_span": null,
+    "teacher_cfg_threshold_a": 0.96,
+    "teacher_guidance_scale": 4.5,
+    "teacher_solver_steps": null,
+    "use_dynamic_shifting": false
+  },
+  "model_config_sha256": {
+    "pipeline": "b5e97ca0d3c0cd9a1e3ed91a71bbdd489de7941b23fe038b3aaa9acf36fd1543",
+    "scheduler": "677e1ed36ca0de4ac8cc766ca58869e8649673d5f1d47eb8f8aef511a18ae8f7",
+    "transformer": "b6ea8128277df286573ce1937c36ce42a5a84e976331091ffccb1d05893dc299",
+    "vae": "58557f2439dfa867450caef425b5d11160be8aa9c34d60dbf23a94a6a94cb060"
+  },
+  "model_family": "sd3_5_medium",
+  "model_revision": "b940f670f0eda2d07fbb75229e779da1ad11eb80",
+  "objective": "dmd",
+  "prediction_type": "flow",
+  "same_engine_resume_supported": true,
+  "schema_version": 1,
+  "source_model_id": "stabilityai/stable-diffusion-3.5-medium",
+  "student_layout": "student",
+  "student_optimization_step": 2000,
+  "trainer_state": "trainer_state/optimizer_and_rng.pt"
+}

students/sd35m/seed_42/checkpoint-2000/student/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.34.0",
+  "_name_or_path": "/data/fs201205/wt93384/huggingface/hub/models--stabilityai--stable-diffusion-3.5-medium/snapshots/b940f670f0eda2d07fbb75229e779da1ad11eb80/transformer",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12
+  ],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 384,
+  "qk_norm": "rms_norm",
+  "sample_size": 128
+}

students/sd35m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bcda7066ac23650cd4f2a51b9b5a7526c1174c6eba2a44e2f1424465b1e1f0
+size 4987168128

students/sd35m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80dc4e268bc80e51b60d7e327a133cea43240266841cecf6fe9eb777fc54ea02
+size 4891592464

students/sd35m/seed_42/checkpoint-2000/student/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,916 @@
+{
+  "metadata": {
+    "total_size": 9878655744
+  },
+  "weight_map": {
+    "context_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "norm_out.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "pos_embed.pos_embed": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "pos_embed.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "pos_embed.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.attn2.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.10.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.attn2.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.11.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.attn2.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.12.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn2.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.9.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}

students/sd3m/seed_42/checkpoint-2000/manifest.json

@@ -0,0 +1,52 @@
+{
+  "backend": "sd3m-native",
+  "config_sha256": "140761b1bc5d7739f2eec4cabbf2d08d6274fc04c26cd40727125ba1e85b8cd4",
+  "cross_engine_resume_supported": false,
+  "distributed_world_size": 4,
+  "fake_score_layout": "fake_score",
+  "flow_contract": {
+    "antipodal_teacher_reg": {},
+    "crra_lpips_net": null,
+    "crra_lpips_version": null,
+    "crra_state_distance": "mse",
+    "dmd_cfg_control": 0.96,
+    "dmd_implementation": "sd_distill_classic_v1",
+    "dmd_loss_weighting": "channel_height_mean_keep_width",
+    "dmd_method": "classic",
+    "dmd_sigma_sampling": "points_mode_c",
+    "dmd_student_fake_sample_coupling": "reuse_last_fake_rollout",
+    "dmd_student_gradient_scope": "local_interval",
+    "fake_score_guidance_scale": 1.0,
+    "fake_teacher_anchor_enabled": true,
+    "fake_updates_per_student": 5,
+    "gad_nsp": {
+      "lambda_nsp": 0.0
+    },
+    "global_unique_prompts_per_student_update": 4,
+    "initial_rollout_noise": "gaussian",
+    "initial_rollout_noise_lowpass_cutoff": null,
+    "initial_rollout_noise_lowpass_fraction": null,
+    "initial_rollout_noise_normalization": null,
+    "initial_rollout_noise_pairing": null,
+    "initial_rollout_noise_support": "full Gaussian",
+    "lambda_fake_teacher_reg": 0.5,
+    "nsp_perturbation": "x_plus_epsilon_v; v~N(0,I) in FP32; fixed detached flow state",
+    "repulsive_expected_pairwise_correlation": null,
+    "repulsive_group_size": null,
+    "shift": 3.0,
+    "student_forwards_per_step": 1,
+    "student_guidance_scale": 1.0,
+    "student_steps": 4,
+    "teacher_cfg_threshold_a": 0.96,
+    "teacher_guidance_scale": 7.0,
+    "teacher_solver_steps": null
+  },
+  "model_family": "sd3_medium",
+  "objective": "tdm",
+  "prediction_type": "flow",
+  "same_engine_resume_supported": true,
+  "schema_version": 1,
+  "student_layout": "student",
+  "student_optimization_step": 2000,
+  "trainer_state": "trainer_state/optimizer_and_rng.pt"
+}

students/sd3m/seed_42/checkpoint-2000/student/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.34.0",
+  "_name_or_path": "/data/fs201205/wt93384/huggingface/hub/models--stabilityai--stable-diffusion-3-medium-diffusers/snapshots/ea42f8cef0f178587cf766dc8129abd379c90671/transformer",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 192,
+  "qk_norm": null,
+  "sample_size": 128
+}

students/sd3m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1671c638ae2dca1f48e421e1d1493a9e7357d156b7b8c5536d042133ecd22f
+size 4968557944

students/sd3m/seed_42/checkpoint-2000/student/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c7195a4537e8cd3e104d2f8ac71006b57efe4b975a0b7af1c052b393783760
+size 3371325672

students/sd3m/seed_42/checkpoint-2000/student/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,690 @@
+{
+  "metadata": {
+    "total_size": 8339804416
+  },
+  "weight_map": {
+    "context_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "norm_out.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "pos_embed.pos_embed": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "pos_embed.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "pos_embed.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "proj_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.text_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_text_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.10.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.11.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.12.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.13.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.13.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.14.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.15.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.16.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.17.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.18.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.19.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.20.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.21.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_add_out.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.ff_context.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.22.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_k_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_q_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_v_proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1_context.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.23.norm1_context.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.5.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.6.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.7.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.8.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_v_proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_add_out.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.ff_context.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.9.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}